"error": "Failed to detect base model #948
Unanswered
jayburton84
asked this question in
Q&A
Replies: 1 comment 1 reply
-
It looks like the models you downloaded are LoRA, not Checkpoints. They are small extensions to checkpoints instead of an entire model. |
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Apologies, I'm new to this and I've been scouring the discussion board for an answer, but I've had no luck solving my issue. Unless I'm missing something, it would appear that I'm not able to utilize any model checkpoints added after initial installation.
I'm running a locally managed server. SD 1.5 and XL workloads are installed, along with the five recommended/default checkpoints (DreamShaper, JuggernautXL, etc) and all control extensions.
I have downloaded about a dozen new models from Civitai - all with a reported base model of SD 1.5 or SDXL - and I placed the .safetensors files here: \krita\ai_diffusion\server\ComfyUI\models\checkpoints. This is the same location that the five recommended/default checkpoints live. Those five default checkpoints are listed in the Model Checkpoint dropdown, but none of the new checkpoints that I downloaded are appearing. I've tried deleting and redownloading in case the files were incomplete.
When I open
127.0.0.1:8188/etn/model_info
, every new checkpoint that I added is listed with the following:"base_model": "unknown", "error": "Failed to detect base model: argument of type 'NoneType' is not iterable"
Whereas the original recommended checkpoints have a base_model correctly identified as either sd15 or sdxl.
I've tried uninstalling and reinstalling, and I also made sure that comfyui-tooling-nodes was replaced with the most updated release. I've watched a bunch of tutorial videos, and everyone makes it look as easy as dragging those .safetensors into the
models/checkpoints
folder and then hitting refresh, but for some reason I'm not having the same experience. Any advice?Beta Was this translation helpful? Give feedback.
All reactions